Use per-vma locking for concurrent page installations, this minimizes
contention with unrelated vmas improving performance. The mmap_lock is
still acquired when needed though, e.g. before get_user_pages_remote().

Many thanks to Barry Song who posted a similar approach [1].

Link: https://lore.kernel.org/all/20240902225009.34576-1-21cnbao@gmail.com/ [1]
Cc: Nhat Pham <nphamcs@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Carlos Llamas <cmllamas@google.com>
---
 drivers/android/binder_alloc.c | 61 +++++++++++++++++++++++++---------
 1 file changed, 45 insertions(+), 16 deletions(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 3716ffd00baf..7d2cad9beebb 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -233,6 +233,48 @@ static inline bool binder_alloc_is_mapped(struct binder_alloc *alloc)
 	return smp_load_acquire(&alloc->mapped);
 }
 
+static struct page *binder_page_lookup(struct binder_alloc *alloc,
+				       unsigned long addr)
+{
+	struct mm_struct *mm = alloc->mm;
+	struct page *page;
+	long ret = 0;
+
+	mmap_read_lock(mm);
+	if (binder_alloc_is_mapped(alloc))
+		ret = get_user_pages_remote(mm, addr, 1, 0, &page, NULL);
+	mmap_read_unlock(mm);
+
+	return ret > 0 ? page : NULL;
+}
+
+static int binder_page_insert(struct binder_alloc *alloc,
+			      unsigned long addr,
+			      struct page *page)
+{
+	struct mm_struct *mm = alloc->mm;
+	struct vm_area_struct *vma;
+	int ret = -ESRCH;
+
+	/* attempt per-vma lock first */
+	vma = lock_vma_under_rcu(mm, addr);
+	if (vma) {
+		if (binder_alloc_is_mapped(alloc))
+			ret = vm_insert_page(vma, addr, page);
+		vma_end_read(vma);
+		return ret;
+	}
+
+	/* fall back to mmap_lock */
+	mmap_read_lock(mm);
+	vma = vma_lookup(mm, addr);
+	if (vma && binder_alloc_is_mapped(alloc))
+		ret = vm_insert_page(vma, addr, page);
+	mmap_read_unlock(mm);
+
+	return ret;
+}
+
 static struct page *binder_page_alloc(struct binder_alloc *alloc,
 				      unsigned long index,
 				      unsigned long addr)
@@ -254,9 +296,7 @@ static int binder_install_single_page(struct binder_alloc *alloc,
 				      unsigned long index,
 				      unsigned long addr)
 {
-	struct vm_area_struct *vma;
 	struct page *page;
-	long npages;
 	int ret;
 
 	if (!mmget_not_zero(alloc->mm))
@@ -268,16 +308,7 @@ static int binder_install_single_page(struct binder_alloc *alloc,
 		goto out;
 	}
 
-	mmap_read_lock(alloc->mm);
-	vma = vma_lookup(alloc->mm, addr);
-	if (!vma || !binder_alloc_is_mapped(alloc)) {
-		__free_page(page);
-		pr_err("%d: %s failed, no vma\n", alloc->pid, __func__);
-		ret = -ESRCH;
-		goto unlock;
-	}
-
-	ret = vm_insert_page(vma, addr, page);
+	ret = binder_page_insert(alloc, addr, page);
 	switch (ret) {
 	case -EBUSY:
 		/*
@@ -287,8 +318,8 @@ static int binder_install_single_page(struct binder_alloc *alloc,
 		 */
 		ret = 0;
 		__free_page(page);
-		npages = get_user_pages_remote(alloc->mm, addr, 1, 0, &page, NULL);
-		if (npages <= 0) {
+		page = binder_page_lookup(alloc, addr);
+		if (!page) {
 			pr_err("%d: failed to find page at offset %lx\n",
 			       alloc->pid, addr - alloc->vm_start);
 			ret = -ESRCH;
@@ -306,8 +337,6 @@ static int binder_install_single_page(struct binder_alloc *alloc,
 		ret = -ENOMEM;
 		break;
 	}
-unlock:
-	mmap_read_unlock(alloc->mm);
 out:
 	mmput_async(alloc->mm);
 	return ret;
-- 
2.47.0.277.g8800431eea-goog